{"id":"W2759066107","doi":"10.1038/s41598-017-13056-1","title":"A machine-learning heuristic to improve gene score prediction of polygenic traits","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hamilton Health Sciences; University of Toronto; McMaster University; Population Health Research Institute","funders":"Cisco Systems","keywords":"Biobank; Linkage disequilibrium; Receiver operating characteristic; Machine learning; Computer science; Artificial intelligence; Statistics; Polygene; Sample size determination; Heuristics; Regression; Genome-wide association study; Single-nucleotide polymorphism; Quantitative trait locus; Mathematics; Bioinformatics; Biology; Genetics; Genotype","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003875518,0.0008008208,0.001411398,0.001766239,0.0004935786,0.0007737973,0.001345412,0.001064992,0.001629431],"category_scores_gemma":[0.01266851,0.0004333693,0.0007112866,0.001101051,0.0008033526,0.0008898714,0.000925492,0.001068094,0.0003288651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00090219,"about_ca_system_score_gemma":0.001555048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003929838,"about_ca_topic_score_gemma":0.003226809,"domain_scores_codex":[0.9986766,0.0007552023,0.00007937563,0.0002111776,0.000149522,0.0001280915],"domain_scores_gemma":[0.9920615,0.006092493,0.0004981015,0.0004095086,0.0007438792,0.0001944805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002274454,0.0002424771,0.01299827,0.00008181212,0.0001206462,0.0001727663,0.00009820862,0.8821115,0.001844568,0.006775158,0.002636361,0.09269085],"study_design_scores_gemma":[0.0000278986,0.00003783239,0.0005097843,0.000008363269,0.00001119332,0.00001662007,0.000006576222,0.9959253,0.000282816,0.003015597,0.0001526652,0.000005250897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2359303,0.0005221714,0.7582068,0.0008527105,0.0001145872,0.0002061656,0.0002221345,0.001146865,0.002798273],"genre_scores_gemma":[0.7980708,0.00007917106,0.1999111,0.0004316663,0.00009354546,0.0001683142,0.0003492982,0.00007377724,0.0008223331],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003929838,"threshold_uncertainty_score":0.02049595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01499254677632753,"score_gpt":0.2594809575558453,"score_spread":0.2444884107795178,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}